sedrickkeh
commited on
Commit
•
a9e1044
1
Parent(s):
9e1ae12
End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +1377 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
4 |
base_model: mistralai/Mistral-7B-v0.1
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: hp_ablations_mistral_epoch5_dcftv1.2
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# hp_ablations_mistral_epoch5_dcftv1.2
|
17 |
|
18 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.4100
|
21 |
|
|
|
4 |
base_model: mistralai/Mistral-7B-v0.1
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: hp_ablations_mistral_epoch5_dcftv1.2
|
|
|
16 |
|
17 |
# hp_ablations_mistral_epoch5_dcftv1.2
|
18 |
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.4100
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.4100167155265808,
|
4 |
+
"eval_runtime": 96.3977,
|
5 |
+
"eval_samples_per_second": 103.374,
|
6 |
+
"eval_steps_per_second": 0.405,
|
7 |
+
"total_flos": 3097981385441280.0,
|
8 |
+
"train_loss": 0.3954814358659693,
|
9 |
+
"train_runtime": 27395.2752,
|
10 |
+
"train_samples_per_second": 34.555,
|
11 |
+
"train_steps_per_second": 0.068
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.4100167155265808,
|
4 |
+
"eval_runtime": 96.3977,
|
5 |
+
"eval_samples_per_second": 103.374,
|
6 |
+
"eval_steps_per_second": 0.405
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 3097981385441280.0,
|
4 |
+
"train_loss": 0.3954814358659693,
|
5 |
+
"train_runtime": 27395.2752,
|
6 |
+
"train_samples_per_second": 34.555,
|
7 |
+
"train_steps_per_second": 0.068
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1377 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1850,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02702702702702703,
|
13 |
+
"grad_norm": 3.48477044162232,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 0.8622,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05405405405405406,
|
20 |
+
"grad_norm": 2.360261766882162,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.6871,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.08108108108108109,
|
27 |
+
"grad_norm": 2.861337031562045,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.6496,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.10810810810810811,
|
34 |
+
"grad_norm": 2.110955586370757,
|
35 |
+
"learning_rate": 5e-06,
|
36 |
+
"loss": 0.6379,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.13513513513513514,
|
41 |
+
"grad_norm": 2.6603965950552375,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.6224,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.16216216216216217,
|
48 |
+
"grad_norm": 2.3295005659015637,
|
49 |
+
"learning_rate": 5e-06,
|
50 |
+
"loss": 0.6158,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.1891891891891892,
|
55 |
+
"grad_norm": 1.4436743736286393,
|
56 |
+
"learning_rate": 5e-06,
|
57 |
+
"loss": 0.6121,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.21621621621621623,
|
62 |
+
"grad_norm": 1.480185038939668,
|
63 |
+
"learning_rate": 5e-06,
|
64 |
+
"loss": 0.6048,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.24324324324324326,
|
69 |
+
"grad_norm": 1.7946241900816966,
|
70 |
+
"learning_rate": 5e-06,
|
71 |
+
"loss": 0.6027,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.2702702702702703,
|
76 |
+
"grad_norm": 2.953041989671829,
|
77 |
+
"learning_rate": 5e-06,
|
78 |
+
"loss": 0.6057,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2972972972972973,
|
83 |
+
"grad_norm": 2.3672617838763292,
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"loss": 0.603,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.32432432432432434,
|
90 |
+
"grad_norm": 2.570180323617788,
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"loss": 0.5968,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.35135135135135137,
|
97 |
+
"grad_norm": 2.4395069709384405,
|
98 |
+
"learning_rate": 5e-06,
|
99 |
+
"loss": 0.5971,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3783783783783784,
|
104 |
+
"grad_norm": 2.139806105177032,
|
105 |
+
"learning_rate": 5e-06,
|
106 |
+
"loss": 0.5967,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.40540540540540543,
|
111 |
+
"grad_norm": 1.8058881040832764,
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"loss": 0.588,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.43243243243243246,
|
118 |
+
"grad_norm": 1.906112223883072,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.5911,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.4594594594594595,
|
125 |
+
"grad_norm": 1.7152010217915816,
|
126 |
+
"learning_rate": 5e-06,
|
127 |
+
"loss": 0.5929,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.4864864864864865,
|
132 |
+
"grad_norm": 1.4638072286809918,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.592,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5135135135135135,
|
139 |
+
"grad_norm": 1.4052441733855927,
|
140 |
+
"learning_rate": 5e-06,
|
141 |
+
"loss": 0.5881,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5405405405405406,
|
146 |
+
"grad_norm": 1.3473253327847512,
|
147 |
+
"learning_rate": 5e-06,
|
148 |
+
"loss": 0.5863,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.5675675675675675,
|
153 |
+
"grad_norm": 1.6317553588784817,
|
154 |
+
"learning_rate": 5e-06,
|
155 |
+
"loss": 0.5888,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5945945945945946,
|
160 |
+
"grad_norm": 1.4742582489032408,
|
161 |
+
"learning_rate": 5e-06,
|
162 |
+
"loss": 0.5846,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.6216216216216216,
|
167 |
+
"grad_norm": 1.3786710575715564,
|
168 |
+
"learning_rate": 5e-06,
|
169 |
+
"loss": 0.5858,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6486486486486487,
|
174 |
+
"grad_norm": 1.3706145590107932,
|
175 |
+
"learning_rate": 5e-06,
|
176 |
+
"loss": 0.5823,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.6756756756756757,
|
181 |
+
"grad_norm": 2.9406828647293684,
|
182 |
+
"learning_rate": 5e-06,
|
183 |
+
"loss": 0.5759,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.7027027027027027,
|
188 |
+
"grad_norm": 1.874695043037241,
|
189 |
+
"learning_rate": 5e-06,
|
190 |
+
"loss": 0.5788,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.7297297297297297,
|
195 |
+
"grad_norm": 1.6258297787646745,
|
196 |
+
"learning_rate": 5e-06,
|
197 |
+
"loss": 0.5807,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7567567567567568,
|
202 |
+
"grad_norm": 1.3370174946548334,
|
203 |
+
"learning_rate": 5e-06,
|
204 |
+
"loss": 0.5753,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.7837837837837838,
|
209 |
+
"grad_norm": 1.4879061874672985,
|
210 |
+
"learning_rate": 5e-06,
|
211 |
+
"loss": 0.5751,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.8108108108108109,
|
216 |
+
"grad_norm": 1.4797771423522537,
|
217 |
+
"learning_rate": 5e-06,
|
218 |
+
"loss": 0.5752,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.8378378378378378,
|
223 |
+
"grad_norm": 1.349831755648445,
|
224 |
+
"learning_rate": 5e-06,
|
225 |
+
"loss": 0.5731,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8648648648648649,
|
230 |
+
"grad_norm": 1.487488462220457,
|
231 |
+
"learning_rate": 5e-06,
|
232 |
+
"loss": 0.5719,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.8918918918918919,
|
237 |
+
"grad_norm": 1.3196199401162108,
|
238 |
+
"learning_rate": 5e-06,
|
239 |
+
"loss": 0.5736,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.918918918918919,
|
244 |
+
"grad_norm": 1.2813534915454334,
|
245 |
+
"learning_rate": 5e-06,
|
246 |
+
"loss": 0.581,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.9459459459459459,
|
251 |
+
"grad_norm": 1.2493996252660173,
|
252 |
+
"learning_rate": 5e-06,
|
253 |
+
"loss": 0.5726,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.972972972972973,
|
258 |
+
"grad_norm": 1.3169592287464336,
|
259 |
+
"learning_rate": 5e-06,
|
260 |
+
"loss": 0.5717,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.0,
|
265 |
+
"grad_norm": 1.6256059905335656,
|
266 |
+
"learning_rate": 5e-06,
|
267 |
+
"loss": 0.5735,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.0,
|
272 |
+
"eval_loss": 0.28570452332496643,
|
273 |
+
"eval_runtime": 96.5261,
|
274 |
+
"eval_samples_per_second": 103.236,
|
275 |
+
"eval_steps_per_second": 0.404,
|
276 |
+
"step": 370
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 1.027027027027027,
|
280 |
+
"grad_norm": 1.7234414441453492,
|
281 |
+
"learning_rate": 5e-06,
|
282 |
+
"loss": 0.4828,
|
283 |
+
"step": 380
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 1.054054054054054,
|
287 |
+
"grad_norm": 1.542357388344519,
|
288 |
+
"learning_rate": 5e-06,
|
289 |
+
"loss": 0.4753,
|
290 |
+
"step": 390
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.0810810810810811,
|
294 |
+
"grad_norm": 1.4861195617131548,
|
295 |
+
"learning_rate": 5e-06,
|
296 |
+
"loss": 0.4799,
|
297 |
+
"step": 400
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.1081081081081081,
|
301 |
+
"grad_norm": 1.4134885594853346,
|
302 |
+
"learning_rate": 5e-06,
|
303 |
+
"loss": 0.4728,
|
304 |
+
"step": 410
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.135135135135135,
|
308 |
+
"grad_norm": 1.8446040240127095,
|
309 |
+
"learning_rate": 5e-06,
|
310 |
+
"loss": 0.4775,
|
311 |
+
"step": 420
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.1621621621621623,
|
315 |
+
"grad_norm": 1.8467841301436136,
|
316 |
+
"learning_rate": 5e-06,
|
317 |
+
"loss": 0.484,
|
318 |
+
"step": 430
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.1891891891891893,
|
322 |
+
"grad_norm": 2.42665171779706,
|
323 |
+
"learning_rate": 5e-06,
|
324 |
+
"loss": 0.4749,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.2162162162162162,
|
329 |
+
"grad_norm": 1.8049502845392928,
|
330 |
+
"learning_rate": 5e-06,
|
331 |
+
"loss": 0.48,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.2432432432432432,
|
336 |
+
"grad_norm": 2.0761863031810375,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.4809,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.2702702702702702,
|
343 |
+
"grad_norm": 2.0655543660952476,
|
344 |
+
"learning_rate": 5e-06,
|
345 |
+
"loss": 0.481,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.2972972972972974,
|
350 |
+
"grad_norm": 1.6759566925998968,
|
351 |
+
"learning_rate": 5e-06,
|
352 |
+
"loss": 0.4764,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.3243243243243243,
|
357 |
+
"grad_norm": 1.396353193003371,
|
358 |
+
"learning_rate": 5e-06,
|
359 |
+
"loss": 0.4761,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.3513513513513513,
|
364 |
+
"grad_norm": 1.397142398326265,
|
365 |
+
"learning_rate": 5e-06,
|
366 |
+
"loss": 0.482,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.3783783783783785,
|
371 |
+
"grad_norm": 1.5036245472795235,
|
372 |
+
"learning_rate": 5e-06,
|
373 |
+
"loss": 0.4817,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.4054054054054055,
|
378 |
+
"grad_norm": 1.5607076153200972,
|
379 |
+
"learning_rate": 5e-06,
|
380 |
+
"loss": 0.4861,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.4324324324324325,
|
385 |
+
"grad_norm": 1.7026202176545633,
|
386 |
+
"learning_rate": 5e-06,
|
387 |
+
"loss": 0.4801,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.4594594594594594,
|
392 |
+
"grad_norm": 1.694705438287125,
|
393 |
+
"learning_rate": 5e-06,
|
394 |
+
"loss": 0.4834,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.4864864864864864,
|
399 |
+
"grad_norm": 1.8913973826320096,
|
400 |
+
"learning_rate": 5e-06,
|
401 |
+
"loss": 0.4815,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.5135135135135136,
|
406 |
+
"grad_norm": 1.3860850720137203,
|
407 |
+
"learning_rate": 5e-06,
|
408 |
+
"loss": 0.4853,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.5405405405405406,
|
413 |
+
"grad_norm": 1.6545389203896799,
|
414 |
+
"learning_rate": 5e-06,
|
415 |
+
"loss": 0.4775,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.5675675675675675,
|
420 |
+
"grad_norm": 1.6330744148753316,
|
421 |
+
"learning_rate": 5e-06,
|
422 |
+
"loss": 0.484,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.5945945945945947,
|
427 |
+
"grad_norm": 1.749422453289866,
|
428 |
+
"learning_rate": 5e-06,
|
429 |
+
"loss": 0.4842,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.6216216216216215,
|
434 |
+
"grad_norm": 1.4714668834139133,
|
435 |
+
"learning_rate": 5e-06,
|
436 |
+
"loss": 0.4815,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.6486486486486487,
|
441 |
+
"grad_norm": 1.7987332350786904,
|
442 |
+
"learning_rate": 5e-06,
|
443 |
+
"loss": 0.4803,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.6756756756756757,
|
448 |
+
"grad_norm": 1.4458046351621974,
|
449 |
+
"learning_rate": 5e-06,
|
450 |
+
"loss": 0.4867,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.7027027027027026,
|
455 |
+
"grad_norm": 1.5250625163041274,
|
456 |
+
"learning_rate": 5e-06,
|
457 |
+
"loss": 0.4898,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.7297297297297298,
|
462 |
+
"grad_norm": 1.682061525596803,
|
463 |
+
"learning_rate": 5e-06,
|
464 |
+
"loss": 0.4903,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.7567567567567568,
|
469 |
+
"grad_norm": 1.725604337448065,
|
470 |
+
"learning_rate": 5e-06,
|
471 |
+
"loss": 0.4832,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.7837837837837838,
|
476 |
+
"grad_norm": 1.451360087475008,
|
477 |
+
"learning_rate": 5e-06,
|
478 |
+
"loss": 0.4825,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.810810810810811,
|
483 |
+
"grad_norm": 1.6609825444761357,
|
484 |
+
"learning_rate": 5e-06,
|
485 |
+
"loss": 0.4826,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.8378378378378377,
|
490 |
+
"grad_norm": 1.9683314087008068,
|
491 |
+
"learning_rate": 5e-06,
|
492 |
+
"loss": 0.4864,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.864864864864865,
|
497 |
+
"grad_norm": 1.6782355490104197,
|
498 |
+
"learning_rate": 5e-06,
|
499 |
+
"loss": 0.485,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.8918918918918919,
|
504 |
+
"grad_norm": 1.9940863134776443,
|
505 |
+
"learning_rate": 5e-06,
|
506 |
+
"loss": 0.4884,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.9189189189189189,
|
511 |
+
"grad_norm": 1.558943375608973,
|
512 |
+
"learning_rate": 5e-06,
|
513 |
+
"loss": 0.4926,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.945945945945946,
|
518 |
+
"grad_norm": 1.2455247588814846,
|
519 |
+
"learning_rate": 5e-06,
|
520 |
+
"loss": 0.4855,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.972972972972973,
|
525 |
+
"grad_norm": 1.4348648241338484,
|
526 |
+
"learning_rate": 5e-06,
|
527 |
+
"loss": 0.4845,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 2.0,
|
532 |
+
"grad_norm": 1.2414831162937485,
|
533 |
+
"learning_rate": 5e-06,
|
534 |
+
"loss": 0.4841,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 2.0,
|
539 |
+
"eval_loss": 0.2870478928089142,
|
540 |
+
"eval_runtime": 96.6141,
|
541 |
+
"eval_samples_per_second": 103.142,
|
542 |
+
"eval_steps_per_second": 0.404,
|
543 |
+
"step": 740
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 2.027027027027027,
|
547 |
+
"grad_norm": 2.327501959947698,
|
548 |
+
"learning_rate": 5e-06,
|
549 |
+
"loss": 0.3857,
|
550 |
+
"step": 750
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 2.054054054054054,
|
554 |
+
"grad_norm": 1.7853879802404622,
|
555 |
+
"learning_rate": 5e-06,
|
556 |
+
"loss": 0.3828,
|
557 |
+
"step": 760
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 2.081081081081081,
|
561 |
+
"grad_norm": 1.6129872542969907,
|
562 |
+
"learning_rate": 5e-06,
|
563 |
+
"loss": 0.3811,
|
564 |
+
"step": 770
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 2.108108108108108,
|
568 |
+
"grad_norm": 1.6822958801213699,
|
569 |
+
"learning_rate": 5e-06,
|
570 |
+
"loss": 0.379,
|
571 |
+
"step": 780
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.135135135135135,
|
575 |
+
"grad_norm": 1.5765921764422512,
|
576 |
+
"learning_rate": 5e-06,
|
577 |
+
"loss": 0.3804,
|
578 |
+
"step": 790
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.1621621621621623,
|
582 |
+
"grad_norm": 1.4901475659604642,
|
583 |
+
"learning_rate": 5e-06,
|
584 |
+
"loss": 0.3877,
|
585 |
+
"step": 800
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 2.189189189189189,
|
589 |
+
"grad_norm": 1.6201893013251834,
|
590 |
+
"learning_rate": 5e-06,
|
591 |
+
"loss": 0.3865,
|
592 |
+
"step": 810
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 2.2162162162162162,
|
596 |
+
"grad_norm": 1.5437549027848532,
|
597 |
+
"learning_rate": 5e-06,
|
598 |
+
"loss": 0.3847,
|
599 |
+
"step": 820
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.2432432432432434,
|
603 |
+
"grad_norm": 1.8632952369866993,
|
604 |
+
"learning_rate": 5e-06,
|
605 |
+
"loss": 0.392,
|
606 |
+
"step": 830
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 2.27027027027027,
|
610 |
+
"grad_norm": 1.7661982815559183,
|
611 |
+
"learning_rate": 5e-06,
|
612 |
+
"loss": 0.394,
|
613 |
+
"step": 840
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.2972972972972974,
|
617 |
+
"grad_norm": 1.7332904607598014,
|
618 |
+
"learning_rate": 5e-06,
|
619 |
+
"loss": 0.3879,
|
620 |
+
"step": 850
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.3243243243243246,
|
624 |
+
"grad_norm": 2.252072555591542,
|
625 |
+
"learning_rate": 5e-06,
|
626 |
+
"loss": 0.3904,
|
627 |
+
"step": 860
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 2.3513513513513513,
|
631 |
+
"grad_norm": 1.6253901818998244,
|
632 |
+
"learning_rate": 5e-06,
|
633 |
+
"loss": 0.397,
|
634 |
+
"step": 870
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.3783783783783785,
|
638 |
+
"grad_norm": 2.211017287566556,
|
639 |
+
"learning_rate": 5e-06,
|
640 |
+
"loss": 0.3931,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.4054054054054053,
|
645 |
+
"grad_norm": 2.398472470432874,
|
646 |
+
"learning_rate": 5e-06,
|
647 |
+
"loss": 0.3938,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.4324324324324325,
|
652 |
+
"grad_norm": 1.5682213825969358,
|
653 |
+
"learning_rate": 5e-06,
|
654 |
+
"loss": 0.3916,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.4594594594594597,
|
659 |
+
"grad_norm": 2.1044553282329077,
|
660 |
+
"learning_rate": 5e-06,
|
661 |
+
"loss": 0.3881,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.4864864864864864,
|
666 |
+
"grad_norm": 1.7564401087246682,
|
667 |
+
"learning_rate": 5e-06,
|
668 |
+
"loss": 0.391,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.5135135135135136,
|
673 |
+
"grad_norm": 1.6382220101052676,
|
674 |
+
"learning_rate": 5e-06,
|
675 |
+
"loss": 0.391,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.5405405405405403,
|
680 |
+
"grad_norm": 1.4798359424940517,
|
681 |
+
"learning_rate": 5e-06,
|
682 |
+
"loss": 0.3979,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.5675675675675675,
|
687 |
+
"grad_norm": 1.4676265261223125,
|
688 |
+
"learning_rate": 5e-06,
|
689 |
+
"loss": 0.3963,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.5945945945945947,
|
694 |
+
"grad_norm": 1.6295486852060186,
|
695 |
+
"learning_rate": 5e-06,
|
696 |
+
"loss": 0.399,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.6216216216216215,
|
701 |
+
"grad_norm": 1.6192977742906878,
|
702 |
+
"learning_rate": 5e-06,
|
703 |
+
"loss": 0.4023,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.6486486486486487,
|
708 |
+
"grad_norm": 1.4805451072812197,
|
709 |
+
"learning_rate": 5e-06,
|
710 |
+
"loss": 0.4037,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.6756756756756754,
|
715 |
+
"grad_norm": 1.6037076836111144,
|
716 |
+
"learning_rate": 5e-06,
|
717 |
+
"loss": 0.4037,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.7027027027027026,
|
722 |
+
"grad_norm": 1.5225333016382139,
|
723 |
+
"learning_rate": 5e-06,
|
724 |
+
"loss": 0.3945,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.72972972972973,
|
729 |
+
"grad_norm": 1.6212777115845565,
|
730 |
+
"learning_rate": 5e-06,
|
731 |
+
"loss": 0.4051,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.756756756756757,
|
736 |
+
"grad_norm": 1.5016437573712755,
|
737 |
+
"learning_rate": 5e-06,
|
738 |
+
"loss": 0.406,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.7837837837837838,
|
743 |
+
"grad_norm": 1.5902877384401621,
|
744 |
+
"learning_rate": 5e-06,
|
745 |
+
"loss": 0.4029,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.810810810810811,
|
750 |
+
"grad_norm": 1.3912722358421692,
|
751 |
+
"learning_rate": 5e-06,
|
752 |
+
"loss": 0.4055,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.8378378378378377,
|
757 |
+
"grad_norm": 1.5492106652733648,
|
758 |
+
"learning_rate": 5e-06,
|
759 |
+
"loss": 0.4046,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.864864864864865,
|
764 |
+
"grad_norm": 1.5663312579126816,
|
765 |
+
"learning_rate": 5e-06,
|
766 |
+
"loss": 0.4016,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.891891891891892,
|
771 |
+
"grad_norm": 1.40383114587804,
|
772 |
+
"learning_rate": 5e-06,
|
773 |
+
"loss": 0.4079,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.918918918918919,
|
778 |
+
"grad_norm": 1.6190187870975588,
|
779 |
+
"learning_rate": 5e-06,
|
780 |
+
"loss": 0.4049,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.945945945945946,
|
785 |
+
"grad_norm": 1.640627877455668,
|
786 |
+
"learning_rate": 5e-06,
|
787 |
+
"loss": 0.4065,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.972972972972973,
|
792 |
+
"grad_norm": 1.4897415581729503,
|
793 |
+
"learning_rate": 5e-06,
|
794 |
+
"loss": 0.4066,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 3.0,
|
799 |
+
"grad_norm": 1.4711135774031523,
|
800 |
+
"learning_rate": 5e-06,
|
801 |
+
"loss": 0.408,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 3.0,
|
806 |
+
"eval_loss": 0.3071748912334442,
|
807 |
+
"eval_runtime": 96.698,
|
808 |
+
"eval_samples_per_second": 103.053,
|
809 |
+
"eval_steps_per_second": 0.403,
|
810 |
+
"step": 1110
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 3.027027027027027,
|
814 |
+
"grad_norm": 2.6131814809186613,
|
815 |
+
"learning_rate": 5e-06,
|
816 |
+
"loss": 0.2928,
|
817 |
+
"step": 1120
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 3.054054054054054,
|
821 |
+
"grad_norm": 2.2485831495990847,
|
822 |
+
"learning_rate": 5e-06,
|
823 |
+
"loss": 0.2851,
|
824 |
+
"step": 1130
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 3.081081081081081,
|
828 |
+
"grad_norm": 1.928587031956844,
|
829 |
+
"learning_rate": 5e-06,
|
830 |
+
"loss": 0.2828,
|
831 |
+
"step": 1140
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 3.108108108108108,
|
835 |
+
"grad_norm": 1.743854950076673,
|
836 |
+
"learning_rate": 5e-06,
|
837 |
+
"loss": 0.2809,
|
838 |
+
"step": 1150
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 3.135135135135135,
|
842 |
+
"grad_norm": 1.8950206315568565,
|
843 |
+
"learning_rate": 5e-06,
|
844 |
+
"loss": 0.2814,
|
845 |
+
"step": 1160
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 3.1621621621621623,
|
849 |
+
"grad_norm": 1.9383522044886479,
|
850 |
+
"learning_rate": 5e-06,
|
851 |
+
"loss": 0.2865,
|
852 |
+
"step": 1170
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 3.189189189189189,
|
856 |
+
"grad_norm": 1.9203849142483256,
|
857 |
+
"learning_rate": 5e-06,
|
858 |
+
"loss": 0.2851,
|
859 |
+
"step": 1180
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 3.2162162162162162,
|
863 |
+
"grad_norm": 1.9070432540284974,
|
864 |
+
"learning_rate": 5e-06,
|
865 |
+
"loss": 0.2874,
|
866 |
+
"step": 1190
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 3.2432432432432434,
|
870 |
+
"grad_norm": 1.9642273546651734,
|
871 |
+
"learning_rate": 5e-06,
|
872 |
+
"loss": 0.2874,
|
873 |
+
"step": 1200
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 3.27027027027027,
|
877 |
+
"grad_norm": 2.371293282521119,
|
878 |
+
"learning_rate": 5e-06,
|
879 |
+
"loss": 0.2921,
|
880 |
+
"step": 1210
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 3.2972972972972974,
|
884 |
+
"grad_norm": 2.69733157052314,
|
885 |
+
"learning_rate": 5e-06,
|
886 |
+
"loss": 0.2891,
|
887 |
+
"step": 1220
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 3.3243243243243246,
|
891 |
+
"grad_norm": 2.4462972161470073,
|
892 |
+
"learning_rate": 5e-06,
|
893 |
+
"loss": 0.287,
|
894 |
+
"step": 1230
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 3.3513513513513513,
|
898 |
+
"grad_norm": 2.09306288923572,
|
899 |
+
"learning_rate": 5e-06,
|
900 |
+
"loss": 0.2895,
|
901 |
+
"step": 1240
|
902 |
+
},
|
903 |
+
{
|
904 |
+
"epoch": 3.3783783783783785,
|
905 |
+
"grad_norm": 2.260854207612739,
|
906 |
+
"learning_rate": 5e-06,
|
907 |
+
"loss": 0.2865,
|
908 |
+
"step": 1250
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 3.4054054054054053,
|
912 |
+
"grad_norm": 2.692817562351766,
|
913 |
+
"learning_rate": 5e-06,
|
914 |
+
"loss": 0.2899,
|
915 |
+
"step": 1260
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 3.4324324324324325,
|
919 |
+
"grad_norm": 3.125964731548184,
|
920 |
+
"learning_rate": 5e-06,
|
921 |
+
"loss": 0.2907,
|
922 |
+
"step": 1270
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 3.4594594594594597,
|
926 |
+
"grad_norm": 2.442243961667573,
|
927 |
+
"learning_rate": 5e-06,
|
928 |
+
"loss": 0.291,
|
929 |
+
"step": 1280
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 3.4864864864864864,
|
933 |
+
"grad_norm": 2.0307566267966344,
|
934 |
+
"learning_rate": 5e-06,
|
935 |
+
"loss": 0.2934,
|
936 |
+
"step": 1290
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 3.5135135135135136,
|
940 |
+
"grad_norm": 2.098894756875353,
|
941 |
+
"learning_rate": 5e-06,
|
942 |
+
"loss": 0.2878,
|
943 |
+
"step": 1300
|
944 |
+
},
|
945 |
+
{
|
946 |
+
"epoch": 3.5405405405405403,
|
947 |
+
"grad_norm": 2.1484942546619985,
|
948 |
+
"learning_rate": 5e-06,
|
949 |
+
"loss": 0.2918,
|
950 |
+
"step": 1310
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 3.5675675675675675,
|
954 |
+
"grad_norm": 1.8339116955180341,
|
955 |
+
"learning_rate": 5e-06,
|
956 |
+
"loss": 0.2943,
|
957 |
+
"step": 1320
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 3.5945945945945947,
|
961 |
+
"grad_norm": 1.9887758275282583,
|
962 |
+
"learning_rate": 5e-06,
|
963 |
+
"loss": 0.2925,
|
964 |
+
"step": 1330
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 3.6216216216216215,
|
968 |
+
"grad_norm": 1.9845485688385418,
|
969 |
+
"learning_rate": 5e-06,
|
970 |
+
"loss": 0.2955,
|
971 |
+
"step": 1340
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 3.6486486486486487,
|
975 |
+
"grad_norm": 1.969672930852857,
|
976 |
+
"learning_rate": 5e-06,
|
977 |
+
"loss": 0.2988,
|
978 |
+
"step": 1350
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 3.6756756756756754,
|
982 |
+
"grad_norm": 1.7604665753983029,
|
983 |
+
"learning_rate": 5e-06,
|
984 |
+
"loss": 0.2954,
|
985 |
+
"step": 1360
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 3.7027027027027026,
|
989 |
+
"grad_norm": 1.8509109071012708,
|
990 |
+
"learning_rate": 5e-06,
|
991 |
+
"loss": 0.2962,
|
992 |
+
"step": 1370
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 3.72972972972973,
|
996 |
+
"grad_norm": 1.6839851527778709,
|
997 |
+
"learning_rate": 5e-06,
|
998 |
+
"loss": 0.2991,
|
999 |
+
"step": 1380
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 3.756756756756757,
|
1003 |
+
"grad_norm": 1.9195065233001387,
|
1004 |
+
"learning_rate": 5e-06,
|
1005 |
+
"loss": 0.2997,
|
1006 |
+
"step": 1390
|
1007 |
+
},
|
1008 |
+
{
|
1009 |
+
"epoch": 3.7837837837837838,
|
1010 |
+
"grad_norm": 2.0352568345546262,
|
1011 |
+
"learning_rate": 5e-06,
|
1012 |
+
"loss": 0.3012,
|
1013 |
+
"step": 1400
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 3.810810810810811,
|
1017 |
+
"grad_norm": 1.8158735733043123,
|
1018 |
+
"learning_rate": 5e-06,
|
1019 |
+
"loss": 0.3005,
|
1020 |
+
"step": 1410
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 3.8378378378378377,
|
1024 |
+
"grad_norm": 1.9516953165324797,
|
1025 |
+
"learning_rate": 5e-06,
|
1026 |
+
"loss": 0.3022,
|
1027 |
+
"step": 1420
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"epoch": 3.864864864864865,
|
1031 |
+
"grad_norm": 1.863346672591352,
|
1032 |
+
"learning_rate": 5e-06,
|
1033 |
+
"loss": 0.3018,
|
1034 |
+
"step": 1430
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 3.891891891891892,
|
1038 |
+
"grad_norm": 1.8751695571197564,
|
1039 |
+
"learning_rate": 5e-06,
|
1040 |
+
"loss": 0.3019,
|
1041 |
+
"step": 1440
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 3.918918918918919,
|
1045 |
+
"grad_norm": 1.9801631273484928,
|
1046 |
+
"learning_rate": 5e-06,
|
1047 |
+
"loss": 0.307,
|
1048 |
+
"step": 1450
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 3.945945945945946,
|
1052 |
+
"grad_norm": 2.003514563060868,
|
1053 |
+
"learning_rate": 5e-06,
|
1054 |
+
"loss": 0.3058,
|
1055 |
+
"step": 1460
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 3.972972972972973,
|
1059 |
+
"grad_norm": 2.0763911612682837,
|
1060 |
+
"learning_rate": 5e-06,
|
1061 |
+
"loss": 0.3032,
|
1062 |
+
"step": 1470
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 4.0,
|
1066 |
+
"grad_norm": 2.336230273567409,
|
1067 |
+
"learning_rate": 5e-06,
|
1068 |
+
"loss": 0.3066,
|
1069 |
+
"step": 1480
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 4.0,
|
1073 |
+
"eval_loss": 0.3498997688293457,
|
1074 |
+
"eval_runtime": 96.4986,
|
1075 |
+
"eval_samples_per_second": 103.266,
|
1076 |
+
"eval_steps_per_second": 0.404,
|
1077 |
+
"step": 1480
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 4.027027027027027,
|
1081 |
+
"grad_norm": 3.0158703873058617,
|
1082 |
+
"learning_rate": 5e-06,
|
1083 |
+
"loss": 0.1986,
|
1084 |
+
"step": 1490
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 4.054054054054054,
|
1088 |
+
"grad_norm": 2.369544566010332,
|
1089 |
+
"learning_rate": 5e-06,
|
1090 |
+
"loss": 0.1914,
|
1091 |
+
"step": 1500
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 4.081081081081081,
|
1095 |
+
"grad_norm": 2.183015942133232,
|
1096 |
+
"learning_rate": 5e-06,
|
1097 |
+
"loss": 0.1906,
|
1098 |
+
"step": 1510
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 4.108108108108108,
|
1102 |
+
"grad_norm": 2.158995110143315,
|
1103 |
+
"learning_rate": 5e-06,
|
1104 |
+
"loss": 0.1894,
|
1105 |
+
"step": 1520
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 4.135135135135135,
|
1109 |
+
"grad_norm": 2.15897438632279,
|
1110 |
+
"learning_rate": 5e-06,
|
1111 |
+
"loss": 0.1923,
|
1112 |
+
"step": 1530
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 4.162162162162162,
|
1116 |
+
"grad_norm": 2.3012908533453316,
|
1117 |
+
"learning_rate": 5e-06,
|
1118 |
+
"loss": 0.1918,
|
1119 |
+
"step": 1540
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 4.1891891891891895,
|
1123 |
+
"grad_norm": 2.3397981392039133,
|
1124 |
+
"learning_rate": 5e-06,
|
1125 |
+
"loss": 0.1955,
|
1126 |
+
"step": 1550
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 4.216216216216216,
|
1130 |
+
"grad_norm": 2.3318950522877544,
|
1131 |
+
"learning_rate": 5e-06,
|
1132 |
+
"loss": 0.1967,
|
1133 |
+
"step": 1560
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 4.243243243243243,
|
1137 |
+
"grad_norm": 2.2558016269733017,
|
1138 |
+
"learning_rate": 5e-06,
|
1139 |
+
"loss": 0.1973,
|
1140 |
+
"step": 1570
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 4.27027027027027,
|
1144 |
+
"grad_norm": 2.0308981605993557,
|
1145 |
+
"learning_rate": 5e-06,
|
1146 |
+
"loss": 0.2001,
|
1147 |
+
"step": 1580
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 4.297297297297297,
|
1151 |
+
"grad_norm": 2.2105682816818604,
|
1152 |
+
"learning_rate": 5e-06,
|
1153 |
+
"loss": 0.1999,
|
1154 |
+
"step": 1590
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 4.324324324324325,
|
1158 |
+
"grad_norm": 2.0611643054991777,
|
1159 |
+
"learning_rate": 5e-06,
|
1160 |
+
"loss": 0.1977,
|
1161 |
+
"step": 1600
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 4.351351351351352,
|
1165 |
+
"grad_norm": 2.244438029380733,
|
1166 |
+
"learning_rate": 5e-06,
|
1167 |
+
"loss": 0.1988,
|
1168 |
+
"step": 1610
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 4.378378378378378,
|
1172 |
+
"grad_norm": 2.1171487595846683,
|
1173 |
+
"learning_rate": 5e-06,
|
1174 |
+
"loss": 0.2016,
|
1175 |
+
"step": 1620
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 4.405405405405405,
|
1179 |
+
"grad_norm": 2.129014172266156,
|
1180 |
+
"learning_rate": 5e-06,
|
1181 |
+
"loss": 0.2045,
|
1182 |
+
"step": 1630
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 4.4324324324324325,
|
1186 |
+
"grad_norm": 2.0849845815435284,
|
1187 |
+
"learning_rate": 5e-06,
|
1188 |
+
"loss": 0.2049,
|
1189 |
+
"step": 1640
|
1190 |
+
},
|
1191 |
+
{
|
1192 |
+
"epoch": 4.45945945945946,
|
1193 |
+
"grad_norm": 2.107058909660221,
|
1194 |
+
"learning_rate": 5e-06,
|
1195 |
+
"loss": 0.2058,
|
1196 |
+
"step": 1650
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 4.486486486486487,
|
1200 |
+
"grad_norm": 2.4419601951125274,
|
1201 |
+
"learning_rate": 5e-06,
|
1202 |
+
"loss": 0.2063,
|
1203 |
+
"step": 1660
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 4.513513513513513,
|
1207 |
+
"grad_norm": 2.242862620136703,
|
1208 |
+
"learning_rate": 5e-06,
|
1209 |
+
"loss": 0.2079,
|
1210 |
+
"step": 1670
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 4.54054054054054,
|
1214 |
+
"grad_norm": 2.1964969220779498,
|
1215 |
+
"learning_rate": 5e-06,
|
1216 |
+
"loss": 0.2063,
|
1217 |
+
"step": 1680
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 4.5675675675675675,
|
1221 |
+
"grad_norm": 2.144927893368169,
|
1222 |
+
"learning_rate": 5e-06,
|
1223 |
+
"loss": 0.2073,
|
1224 |
+
"step": 1690
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 4.594594594594595,
|
1228 |
+
"grad_norm": 2.4089173007864986,
|
1229 |
+
"learning_rate": 5e-06,
|
1230 |
+
"loss": 0.2064,
|
1231 |
+
"step": 1700
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"epoch": 4.621621621621622,
|
1235 |
+
"grad_norm": 2.236620269865094,
|
1236 |
+
"learning_rate": 5e-06,
|
1237 |
+
"loss": 0.208,
|
1238 |
+
"step": 1710
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 4.648648648648649,
|
1242 |
+
"grad_norm": 2.2273265321363964,
|
1243 |
+
"learning_rate": 5e-06,
|
1244 |
+
"loss": 0.2091,
|
1245 |
+
"step": 1720
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 4.675675675675675,
|
1249 |
+
"grad_norm": 2.043537478772687,
|
1250 |
+
"learning_rate": 5e-06,
|
1251 |
+
"loss": 0.2083,
|
1252 |
+
"step": 1730
|
1253 |
+
},
|
1254 |
+
{
|
1255 |
+
"epoch": 4.702702702702703,
|
1256 |
+
"grad_norm": 2.2566729233438516,
|
1257 |
+
"learning_rate": 5e-06,
|
1258 |
+
"loss": 0.2099,
|
1259 |
+
"step": 1740
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 4.72972972972973,
|
1263 |
+
"grad_norm": 2.3414348548757853,
|
1264 |
+
"learning_rate": 5e-06,
|
1265 |
+
"loss": 0.2107,
|
1266 |
+
"step": 1750
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 4.756756756756757,
|
1270 |
+
"grad_norm": 2.231457361542356,
|
1271 |
+
"learning_rate": 5e-06,
|
1272 |
+
"loss": 0.2096,
|
1273 |
+
"step": 1760
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 4.783783783783784,
|
1277 |
+
"grad_norm": 2.182368419604419,
|
1278 |
+
"learning_rate": 5e-06,
|
1279 |
+
"loss": 0.2111,
|
1280 |
+
"step": 1770
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 4.8108108108108105,
|
1284 |
+
"grad_norm": 2.3022522015009526,
|
1285 |
+
"learning_rate": 5e-06,
|
1286 |
+
"loss": 0.2097,
|
1287 |
+
"step": 1780
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 4.837837837837838,
|
1291 |
+
"grad_norm": 2.154576582443656,
|
1292 |
+
"learning_rate": 5e-06,
|
1293 |
+
"loss": 0.2132,
|
1294 |
+
"step": 1790
|
1295 |
+
},
|
1296 |
+
{
|
1297 |
+
"epoch": 4.864864864864865,
|
1298 |
+
"grad_norm": 2.185745168624507,
|
1299 |
+
"learning_rate": 5e-06,
|
1300 |
+
"loss": 0.212,
|
1301 |
+
"step": 1800
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 4.891891891891892,
|
1305 |
+
"grad_norm": 2.1651574566981395,
|
1306 |
+
"learning_rate": 5e-06,
|
1307 |
+
"loss": 0.2143,
|
1308 |
+
"step": 1810
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 4.918918918918919,
|
1312 |
+
"grad_norm": 2.2200846915512127,
|
1313 |
+
"learning_rate": 5e-06,
|
1314 |
+
"loss": 0.2137,
|
1315 |
+
"step": 1820
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 4.945945945945946,
|
1319 |
+
"grad_norm": 2.344248992891754,
|
1320 |
+
"learning_rate": 5e-06,
|
1321 |
+
"loss": 0.2162,
|
1322 |
+
"step": 1830
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 4.972972972972973,
|
1326 |
+
"grad_norm": 2.150842096847866,
|
1327 |
+
"learning_rate": 5e-06,
|
1328 |
+
"loss": 0.215,
|
1329 |
+
"step": 1840
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 5.0,
|
1333 |
+
"grad_norm": 2.3030280373590335,
|
1334 |
+
"learning_rate": 5e-06,
|
1335 |
+
"loss": 0.2144,
|
1336 |
+
"step": 1850
|
1337 |
+
},
|
1338 |
+
{
|
1339 |
+
"epoch": 5.0,
|
1340 |
+
"eval_loss": 0.4100167155265808,
|
1341 |
+
"eval_runtime": 95.571,
|
1342 |
+
"eval_samples_per_second": 104.268,
|
1343 |
+
"eval_steps_per_second": 0.408,
|
1344 |
+
"step": 1850
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 5.0,
|
1348 |
+
"step": 1850,
|
1349 |
+
"total_flos": 3097981385441280.0,
|
1350 |
+
"train_loss": 0.3954814358659693,
|
1351 |
+
"train_runtime": 27395.2752,
|
1352 |
+
"train_samples_per_second": 34.555,
|
1353 |
+
"train_steps_per_second": 0.068
|
1354 |
+
}
|
1355 |
+
],
|
1356 |
+
"logging_steps": 10,
|
1357 |
+
"max_steps": 1850,
|
1358 |
+
"num_input_tokens_seen": 0,
|
1359 |
+
"num_train_epochs": 5,
|
1360 |
+
"save_steps": 500,
|
1361 |
+
"stateful_callbacks": {
|
1362 |
+
"TrainerControl": {
|
1363 |
+
"args": {
|
1364 |
+
"should_epoch_stop": false,
|
1365 |
+
"should_evaluate": false,
|
1366 |
+
"should_log": false,
|
1367 |
+
"should_save": true,
|
1368 |
+
"should_training_stop": true
|
1369 |
+
},
|
1370 |
+
"attributes": {}
|
1371 |
+
}
|
1372 |
+
},
|
1373 |
+
"total_flos": 3097981385441280.0,
|
1374 |
+
"train_batch_size": 8,
|
1375 |
+
"trial_name": null,
|
1376 |
+
"trial_params": null
|
1377 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED